TEXT INDEPENDENT SPEAKER IDENTIFICATION USING LSP CODEBOOK SPEAKER MODELS AND LINEAR DISCRIMINANT FUNCTIONS

R. D. Zilca, Y. Bistritz

Research output: Contribution to conferencePaperpeer-review

Abstract

The popularity of Line Spectra Pairs (LSP) in speech processing has been supported recently by theoretical studies of their statistical properties. It has been shown that LSP frequencies are uncorrelated, and have a diagonal sensitivity matrix with respect to spectral distortion. Therefore, LSP is suitable for Vector Quantization (VQ) schemes with simple weighted Euclidean distance measures. This was further supported by an analysis of the LSP probability density function, shown to be appropriate for distance-based recognition frameworks. This paper reports our study on developing improved methods for using LSP in VQ based speaker recognition. We used Linear Discriminant Analysis (LDA) to explore the speaker-discrimination statistics of LSP, and to transform them into a speaker-discriminative space. Further enhancements include the use of special VQ distance measures such as F-ratio weighting and Inverse Harmonic Measure (IHM). Performance evaluation experiments were conducted on very short speech sessions, using a database of 32 male speakers, taken from the TIMIT and NTIMIT. Identification results of 100% for clean speech and 70% for telephone speech were achieved.

Original languageEnglish
Pages799-802
Number of pages4
StatePublished - 1999
Event6th European Conference on Speech Communication and Technology, EUROSPEECH 1999 - Budapest, Hungary
Duration: 5 Sep 19999 Sep 1999

Conference

Conference6th European Conference on Speech Communication and Technology, EUROSPEECH 1999
Country/TerritoryHungary
CityBudapest
Period5/09/999/09/99

Fingerprint

Dive into the research topics of 'TEXT INDEPENDENT SPEAKER IDENTIFICATION USING LSP CODEBOOK SPEAKER MODELS AND LINEAR DISCRIMINANT FUNCTIONS'. Together they form a unique fingerprint.

Cite this